Fast stitch algorithm on aerial images

Because of high resolution of the aerial images, the existing stitching algorithms´ speed are too slow. In this paper, we propose a fast stitching algorithm. First, we build Gaussian pyramid and select the key pyramid image by image characteristic. Then, we extract feature points and use region removal algorithm to get the key feature matches of an image. Region removal algorithm selects key feature match in a circle region and removes the redundant quantity. It improves the efficiency of image stitching. Finally, we analyze the relationship between the total errors with iteration times of bundle adjustment, which shows that the errors decrease fast at the first 50 iterations. Experiments on two datasets show that, our algorithm improves both the speed and precision.